15 code implementations • 6 Oct 2014 • Devavrat Shah, Kang Zhang
In this paper, we discuss the method of Bayesian regression and its efficacy for predicting price variation of Bitcoin, a recently popularized virtual, cryptographic currency.
1 code implementation • 25 Feb 2018 • Anish Agarwal, Muhammad Jehangir Amjad, Devavrat Shah, Dennis Shen
In effect, this generalizes the widely used Singular Spectrum Analysis (SSA) in time series literature, and allows us to establish a rigorous link between time series analysis and matrix estimation.
1 code implementation • 18 Nov 2017 • Muhammad Jehangir Amjad, Devavrat Shah, Dennis Shen
Our experiments, using both real-world and synthetic datasets, demonstrate that our robust generalization yields an improvement over the classical synthetic control method.
1 code implementation • 5 Jan 2022 • Abdullah Alomar, Pouya Hamadanian, Arash Nasr-Esfahany, Anish Agarwal, Mohammad Alizadeh, Devavrat Shah
Key to CausalSim is mapping unbiased trace-driven simulation to a tensor completion problem with extremely sparse observations.
1 code implementation • 4 Feb 2023 • Arash Nasr-Esfahany, Mohammad Alizadeh, Devavrat Shah
We study counterfactual identifiability in causal models with bijective generation mechanisms (BGM), a class that generalizes several widely-used causal models in the literature.
1 code implementation • 1 Feb 2024 • Rohan Alur, Manish Raghavan, Devavrat Shah
Our approach focuses on the use of human judgment to distinguish inputs which `look the same' to any feasible predictive algorithm.
no code implementations • 23 Mar 2017 • Devavrat Shah, Christina Lee Yu
Inferring the correct answers to binary tasks based on multiple noisy answers in an unsupervised manner has emerged as the canonical question for micro-task crowdsourcing or more generally aggregating opinions.
no code implementations • NeurIPS 2018 • Devavrat Shah, Qiaomin Xie
In particular, for MDPs with a $d$-dimensional state space and the discounted factor $\gamma \in (0, 1)$, given an arbitrary sample path with "covering time" $ L $, we establish that the algorithm is guaranteed to output an $\varepsilon$-accurate estimate of the optimal Q-function using $\tilde{O}\big(L/(\varepsilon^3(1-\gamma)^7)\big)$ samples.
no code implementations • 20 Jul 2015 • Guy Bresler, Devavrat Shah, Luis F. Voloch
There is much empirical evidence that item-item collaborative filtering works well in practice.
no code implementations • 8 Sep 2012 • Sahand Negahban, Sewoong Oh, Devavrat Shah
To study the efficacy of the algorithm, we consider the popular Bradley-Terry-Luce (BTL) model (equivalent to the Multinomial Logit (MNL) for pair-wise comparisons) in which each object has an associated score which determines the probabilistic outcomes of pair-wise comparisons between objects.
no code implementations • 6 Oct 2015 • George Chen, Devavrat Shah, Polina Golland
Despite the popularity and empirical success of patch-based nearest-neighbor and weighted majority voting approaches to medical image segmentation, there has been no theoretical development on when, why, and how well these nonparametric methods work.
no code implementations • NeurIPS 2014 • Guy Bresler, David Gamarnik, Devavrat Shah
In this paper we investigate the computational complexity of learning the graph structure underlying a discrete undirected graphical model from i. i. d.
no code implementations • 28 Oct 2014 • Guy Bresler, David Gamarnik, Devavrat Shah
In this paper we consider the problem of learning undirected graphical models from data generated according to the Glauber dynamics.
no code implementations • NeurIPS 2014 • Sewoong Oh, Devavrat Shah
In case of single MNL models (no mixture), computationally and statistically tractable learning from pair-wise comparisons is feasible.
no code implementations • NeurIPS 2014 • Guy Bresler, George H. Chen, Devavrat Shah
Despite the prevalence of collaborative filtering in recommendation systems, there has been little theoretical development on why and how well it works, especially in the "online" setting, where items are recommended to users over time.
no code implementations • NeurIPS 2014 • Guy Bresler, David Gamarnik, Devavrat Shah
Our proof gives a polynomial time reduction from approximating the partition function of the hard-core model, known to be hard, to learning approximate parameters.
no code implementations • 17 Sep 2014 • Angélique Drémeau, Christophe Schülke, Yingying Xu, Devavrat Shah
These are notes from the lecture of Devavrat Shah given at the autumn school "Statistical Physics, Optimization, Inference, and Message-Passing Algorithms", that took place in Les Houches, France from Monday September 30th, 2013, till Friday October 11th, 2013.
no code implementations • NeurIPS 2013 • George H. Chen, Stanislav Nikolov, Devavrat Shah
Our guiding hypothesis is that in many applications, such as forecasting which topics will become trends on Twitter, there aren't actually that many prototypical time series to begin with, relative to the number of time series we have access to, e. g., topics become trends on Twitter only in a few distinct manners whereas we can collect massive amounts of Twitter data.
no code implementations • 24 Sep 2013 • Vincent Blondel, Kyomin Jung, Pushmeet Kohli, Devavrat Shah
This paper presents a novel meta algorithm, Partition-Merge (PM), which takes existing centralized algorithms for graph computation and makes them distributed and faster.
no code implementations • 17 Oct 2011 • David R. Karger, Sewoong Oh, Devavrat Shah
Further, we compare our approach with a more general class of algorithms which can dynamically assign tasks.
no code implementations • 2 Nov 2010 • Dhruv Parthasarathy, Devavrat Shah, Tauhid Zaman
For a large number of popular social networks, it recovers communities with a much higher F1 score than other popular algorithms.
no code implementations • 15 Oct 2018 • Linqi Song, Christina Fragouli, Devavrat Shah
We consider recommendation systems that need to operate under wireless bandwidth constraints, measured as number of broadcast transmissions, and demonstrate a (tight for some instances) tradeoff between regret and bandwidth for two scenarios: the case of multi-armed bandit with context, and the case where there is a latent structure in the message space that we can exploit to reduce the learning phase.
no code implementations • NeurIPS 2017 • Christian Borgs, Jennifer Chayes, Christina E. Lee, Devavrat Shah
We show that the mean squared error (MSE) of our estimator converges to $0$ at the rate of $O(d^2 (pn)^{-2/5})$ as long as $\omega(d^5 n)$ random entries from a total of $n^2$ entries of $Y$ are observed (uniformly sampled), $\E[Y]$ has rank $d$, and the entries of $Y$ have bounded support.
no code implementations • NeurIPS 2016 • Dogyoon Song, Christina E. Lee, Yihua Li, Devavrat Shah
In contrast with classical regression, the features $x = (x_1(u), x_2(i))$ are not observed, making it challenging to apply standard regression methods to predict the unobserved ratings.
no code implementations • NeurIPS 2013 • Christina E. Lee, Asuman Ozdaglar, Devavrat Shah
In this paper, we provide a novel algorithm that answers whether a chosen state in a MC has stationary probability larger than some $\Delta \in (0, 1)$.
no code implementations • NeurIPS 2012 • Sahand Negahban, Sewoong Oh, Devavrat Shah
In most settings, in addition to obtaining ranking, finding ‘scores’ for each object (e. g. player’s rating) is of interest to understanding the intensity of the preferences.
no code implementations • NeurIPS 2011 • David R. Karger, Sewoong Oh, Devavrat Shah
Crowdsourcing systems, in which tasks are electronically distributed to numerous ``information piece-workers'', have emerged as an effective paradigm for human-powered solving of large scale problems in domains such as image classification, data entry, optical character recognition, recommendation, and proofreading.
no code implementations • NeurIPS 2009 • Vivek Farias, Srikanth Jagabathula, Devavrat Shah
We visit the following fundamental problem: For a `generic model of consumer choice (namely, distributions over preference lists) and a limited amount of data on how consumers actually make decisions (such as marginal preference information), how may one predict revenues from offering a particular assortment of choices?
no code implementations • NeurIPS 2009 • Kyomin Jung, Pushmeet Kohli, Devavrat Shah
We consider the question of computing Maximum A Posteriori (MAP) assignment in an arbitrary pair-wise Markov Random Field (MRF).
no code implementations • NeurIPS 2007 • Kyomin Jung, Devavrat Shah
We present a new local approximation algorithm for computing MAP and log-partition function for arbitrary exponential family distribution represented by a finite-valued pair-wise Markov random field (MRF), say G. Our algorithm is based on decomposing G into appropriately chosen small components; computing estimates locally in each of these components and then producing a good global solution.
no code implementations • ICLR 2019 • Ravichandra Addanki, Mohammad Alizadeh, Shaileshh Bojja Venkatakrishnan, Devavrat Shah, Qiaomin Xie, Zhi Xu
AlphaGo Zero (AGZ) introduced a new {\em tabula rasa} reinforcement learning algorithm that has achieved superhuman performance in the games of Go, Chess, and Shogi with no prior knowledge other than the rules of the game.
no code implementations • 31 Dec 2018 • Devavrat Shah, Dogyoon Song
Despite the success of RUMs in various domains and the versatility of mixture RUMs to capture the heterogeneity in preferences, there has been only limited progress in learning a mixture of RUMs from partial data such as pairwise comparisons.
no code implementations • 14 Feb 2019 • Devavrat Shah, Qiaomin Xie, Zhi Xu
In effect, we establish that to learn an $\varepsilon$ approximation of the value function with respect to $\ell_\infty$ norm, MCTS combined with nearest neighbor requires a sample size scaling as $\widetilde{O}\big(\varepsilon^{-(d+4)}\big)$, where $d$ is the dimension of the state space.
no code implementations • NeurIPS 2019 • Anish Agarwal, Devavrat Shah, Dennis Shen, Dogyoon Song
As an important contribution to the Synthetic Control literature, we establish that an (approximate) linear synthetic control exists in the setting of a generalized factor model; traditionally, the existence of a synthetic control needs to be assumed to exist as an axiom.
no code implementations • 17 Mar 2019 • Anish Agarwal, Abdullah Alomar, Devavrat Shah
Computationally, tspDB is 59-62x and 94-95x faster compared to LSTM and DeepAR in terms of median ML model training time and prediction query latency, respectively.
no code implementations • 3 Aug 2019 • Devavrat Shah, Christina Lee Yu
We prove that the algorithm recovers a finite rank tensor with maximum entry-wise error (MEE) and mean-squared-error (MSE) decaying to $0$ as long as each entry is observed independently with probability $p = \Omega(n^{-3/2 + \kappa})$ for any arbitrarily small $\kappa > 0$.
no code implementations • 1 Nov 2019 • Lavanya Marla, Lav R. Varshney, Devavrat Shah, Nirmal A. Prakash, Michael E. Gale
We show this notion of pipelined network flow is optimized using network paths that are both short and wide, and develop efficient algorithms to compute such paths for given pairs of nodes and for all-pairs.
no code implementations • 25 Feb 2020 • Devavrat Shah, Varun Somani, Qiaomin Xie, Zhi Xu
For a concrete instance of EIS where random policy is used for "exploration", Monte-Carlo Tree Search is used for "policy improvement" and Nearest Neighbors is used for "supervised learning", we establish that this method finds an $\varepsilon$-approximate value function of Nash equilibrium in $\widetilde{O}(\varepsilon^{-(d+4)})$ steps when the underlying state-space of the game is continuous and $d$-dimensional.
no code implementations • 30 Apr 2020 • Anish Agarwal, Abdullah Alomar, Arnab Sarker, Devavrat Shah, Dennis Shen, Cindy Yang
In essence, the method leverages information from different interventions that have already been enacted across the world and fits it to a policy maker's setting of interest, e. g., to estimate the effect of mobility-restricting interventions on the U. S., we use daily death data from countries that enforced severe mobility restrictions to create a "synthetic low mobility U. S." and predict the counterfactual trajectory of the U. S. if it had indeed applied a similar intervention.
no code implementations • L4DC 2020 • Devavrat Shah, Qiaomin Xie, Zhi Xu
As a proof of concept, we propose an RL policy using Sparse-Sampling-based Monte Carlo Oracle and argue that it satisfies the stability property as long as the system dynamics under the optimal policy respects a Lyapunov function.
no code implementations • NeurIPS 2020 • Devavrat Shah, Dogyoon Song, Zhi Xu, Yuzhe Yang
As our key contribution, we develop a simple, iterative learning algorithm that finds $\epsilon$-optimal $Q$-function with sample complexity of $\widetilde{O}(\frac{1}{\epsilon^{\max(d_1, d_2)+2}})$ when the optimal $Q$-function has low rank $r$ and the discounting factor $\gamma$ is below a certain threshold.
no code implementations • 15 Jun 2020 • Ali Jadbabaie, Anuran Makur, Devavrat Shah
In this paper, we study the problem of learning the skill distribution of a population of agents from observations of pairwise games in a tournament.
no code implementations • 13 Jun 2020 • Anish Agarwal, Devavrat Shah, Dennis Shen
Towards this, we present a causal framework, synthetic interventions (SI), to infer these $N \times D$ causal parameters while only observing each of the $N$ units under at most two interventions, independent of $D$.
no code implementations • 24 Jun 2020 • Anish Agarwal, Abdullah Alomar, Devavrat Shah
We introduce and analyze a variant of multivariate singular spectrum analysis (mSSA), a popular time series method to impute and forecast a multivariate time series.
1 code implementation • 27 Oct 2020 • Anish Agarwal, Devavrat Shah, Dennis Shen
To the best of our knowledge, our prediction guarantees for the fixed design setting have been elusive in both the high-dimensional error-in-variables and synthetic controls literatures.
no code implementations • 28 Oct 2020 • Abhin Shah, Devavrat Shah, Gregory W. Wornell
We consider learning a sparse pairwise Markov Random Field (MRF) with continuous-valued variables from i. i. d samples.
no code implementations • 4 Nov 2020 • Ali Jadbabaie, Anuran Makur, Devavrat Shah
In contrast, we demonstrate that when the loss function is smooth in the data, we can learn the oracle at every iteration and beat the oracle complexities of both GD and SGD in important regimes.
no code implementations • NeurIPS 2020 • Ali Jadbabaie, Anuran Makur, Devavrat Shah
In this paper, we study the problem of learning the skill distribution of a population of agents from observations of pairwise games in a tournament.
no code implementations • 11 Feb 2021 • Sarah H. Cen, Devavrat Shah
In this work, we study how competition affects the long-term outcomes of individuals as they learn.
no code implementations • NeurIPS 2021 • Anish Agarwal, Abdullah Alomar, Varkey Alumootil, Devavrat Shah, Dennis Shen, Zhi Xu, Cindy Yang
We consider offline reinforcement learning (RL) with heterogeneous agents under severe data scarcity, i. e., we only observe a single historical trajectory for every agent under an unknown, potentially sub-optimal policy.
no code implementations • 19 Feb 2021 • Romain Cosson, Devavrat Shah
Specifically, we argue that (a variant of) TRW produces an estimate that is within factor $\frac{1}{\sqrt{\kappa(G)}}$ of the true log-partition function for any discrete pairwise graphical model over graph $G$, where $\kappa(G) \in (0, 1]$ captures how far $G$ is from tree structure with $\kappa(G) = 1$ for trees and $2/N$ for the complete graph over $N$ vertices.
no code implementations • 30 Sep 2021 • Anish Agarwal, Munther Dahleh, Devavrat Shah, Dennis Shen
In particular, we establish entry-wise, i. e., max-norm, finite-sample consistency and asymptotic normality results for matrix completion with MNAR data.
no code implementations • NeurIPS 2021 • Abhin Shah, Devavrat Shah, Gregory W. Wornell
In this work, we propose a computationally efficient estimator that is consistent as well as asymptotically normal under mild conditions.
no code implementations • NeurIPS 2021 • Arwa Alanqary, Abdullah Alomar, Devavrat Shah
The change point in such a setting corresponds to a change in the underlying spatio-temporal model.
no code implementations • 29 Dec 2021 • Ali Jadbabaie, Horia Mania, Devavrat Shah, Suvrit Sra
We revisit a model for time-varying linear regression that assumes the unknown parameters evolve according to a linear dynamical system.
no code implementations • 6 Jan 2022 • Ali Jadbabaie, Anuran Makur, Devavrat Shah
Under some assumptions on the loss function, e. g., strong convexity in parameter, $\eta$-H\"older smoothness in data, etc., we prove that the federated oracle complexity of FedLRGD scales like $\phi m(p/\epsilon)^{\Theta(d/\eta)}$ and that of FedAve scales like $\phi m(p/\epsilon)^{3/4}$ (neglecting sub-dominant factors), where $\phi\gg 1$ is a "communication-to-computation ratio," $p$ is the parameter dimension, and $d$ is the data dimension.
no code implementations • 7 Jan 2022 • Arnab Sarker, Ali Jadbabaie, Devavrat Shah
The model represents time series of cases and fatalities as a mixture of Gaussian curves, providing a flexible function class to learn from data compared to traditional mechanistic models.
no code implementations • 14 Feb 2022 • Raaz Dwivedi, Katherine Tian, Sabina Tomkins, Predrag Klasnja, Susan Murphy, Devavrat Shah
Our goal is to provide inference guarantees for the counterfactual mean at the smallest possible scale -- mean outcome under different treatments for each unit and each time -- with minimal assumptions on the adaptive treatment policy.
no code implementations • 29 Mar 2022 • Ali Jadbabaie, Arnab Sarker, Devavrat Shah
Successful predictive modeling of epidemics requires an understanding of the implicit feedback control strategies which are implemented by populations to modulate the spread of contagion.
no code implementations • 16 Jun 2022 • Romain Cosson, Ali Jadbabaie, Anuran Makur, Amirhossein Reisizadeh, Devavrat Shah
When $r \ll p$, these complexities are smaller than the known complexities of $\mathcal{O}(p \log(1/\epsilon))$ and $\mathcal{O}(p/\epsilon^2)$ of {\gd} in the strongly convex and non-convex settings, respectively.
no code implementations • 20 Oct 2022 • Anish Agarwal, Sarah H. Cen, Devavrat Shah, Christina Lee Yu
We propose an estimator, Network Synthetic Interventions (NSI), and show that it consistently estimates the mean outcomes for a unit under an arbitrary set of counterfactual treatments for the network.
no code implementations • 14 Nov 2022 • Abhin Shah, Raaz Dwivedi, Devavrat Shah, Gregory W. Wornell
Given an observational study with $n$ independent but heterogeneous units, our goal is to learn the counterfactual distribution for each unit using only one $p$-dimensional sample per unit containing covariates, interventions, and outcomes.
no code implementations • 25 Nov 2022 • Raaz Dwivedi, Katherine Tian, Sabina Tomkins, Predrag Klasnja, Susan Murphy, Devavrat Shah
We consider a matrix completion problem with missing data, where the $(i, t)$-th entry, when observed, is given by its mean $f(u_i, v_t)$ plus mean-zero noise for an unknown function $f$ and latent factors $u_i$ and $v_t$.
no code implementations • 4 Feb 2023 • Cindy Y. Zhang, Sarah H. Cen, Devavrat Shah
Specifically, we show that using a popular ME method known as singular value thresholding (SVT) to pre-process the data provides a strong IF guarantee under appropriate conditions.
no code implementations • 20 Apr 2023 • Sarah H. Cen, Aleksander Madry, Devavrat Shah
In particular, we introduce the notion of a baseline feed: the content that a user would see without filtering (e. g., on Twitter, this could be the chronological timeline).
no code implementations • NeurIPS 2023 • Abdullah Alomar, Munther Dahleh, Sean Mann, Devavrat Shah
However, a theoretical underpinning of multi-stage learning algorithms involving both deterministic and stationary components has been absent in the literature despite its pervasiveness.
no code implementations • 7 Jun 2023 • Yassir Jedra, Sean Mann, Charlotte Park, Devavrat Shah
Instead of treating this observation bias as a disadvantage, as is typically the case, the goal is to exploit the shared information between the bias and the outcome of interest to improve predictions.
no code implementations • 12 Sep 2023 • Abhin Shah, Devavrat Shah, Gregory W. Wornell
While the traditional maximum likelihood estimator for this class of exponential family is consistent, asymptotically normal, and asymptotically efficient, evaluating it is computationally hard.
no code implementations • 4 Nov 2023 • Bowen Song, Marco Paolieri, Harper E. Stewart, Leana Golubchik, Jill L. McNitt-Gray, Vishal Misra, Devavrat Shah
Our aim in this paper is to determine if data collected with inertial measurement units (IMUs), that can be worn by athletes during outdoor runs, can be used to predict GRF with sufficient accuracy to allow the analysis of its derived biomechanical variables (e. g., contact time and loading rate).
1 code implementation • NeurIPS 2023 • Rohan Alur, Loren Laine, Darrick K. Li, Manish Raghavan, Devavrat Shah, Dennis Shung
A rejection of our test thus suggests that human experts may add value to any algorithm trained on the available data, and has direct implications for whether human-AI `complementarity' is achievable in a given prediction task.
no code implementations • 22 Feb 2024 • Jessy Xinyi Han, Andrew Miller, S. Craig Watkins, Christopher Winship, Fotini Christia, Devavrat Shah
We provide a theoretical characterization and an associated data-driven method to evaluate (a) the presence of any form of racial bias, and (b) if so, the primary source of such a bias in terms of race and criminality.